DCVNet: Dilated Cost Volume Networks for Fast Optical Flow
This addresses the problem of slow optical flow estimation for computer vision applications, offering a faster alternative to existing methods, though it is incremental as it builds on prior cost volume techniques.
The paper tackles the computational burden of building cost volumes for optical flow by proposing DCVNet, which uses dilated cost volumes to capture small and large displacements simultaneously, achieving comparable accuracy and real-time inference at 30 fps on a 1080ti GPU.
The cost volume, capturing the similarity of possible correspondences across two input images, is a key ingredient in state-of-the-art optical flow approaches. When sampling correspondences to build the cost volume, a large neighborhood radius is required to deal with large displacements, introducing a significant computational burden. To address this, coarse-to-fine or recurrent processing of the cost volume is usually adopted, where correspondence sampling in a local neighborhood with a small radius suffices. In this paper, we propose an alternative by constructing cost volumes with different dilation factors to capture small and large displacements simultaneously. A U-Net with skip connections is employed to convert the dilated cost volumes into interpolation weights between all possible captured displacements to get the optical flow. Our proposed model DCVNet only needs to process the cost volume once in a simple feedforward manner and does not rely on the sequential processing strategy. DCVNet obtains comparable accuracy to existing approaches and achieves real-time inference (30 fps on a mid-end 1080ti GPU). The code and model weights are available at https://github.com/neu-vi/ezflow.